Deep learning predicted future culprit lesions with an AUC of 0.81, outperforming diameter stenosis (AUC 0.62, p=0.04), area stenosis (AUC 0.58, p=0.05), and human visual assessment.
Observational
Does deep learning improve the prediction of future culprit lesions responsible for myocardial infarction compared to human visual assessment and standard angiographic parameters in patients with non-significant CAD?
Deep learning applied to invasive coronary angiography images outperforms human visual assessment and standard angiographic parameters in predicting future culprit lesions for myocardial infarction.
Effect estimate: AUC 0.81
p-value: p=0.04
BACKGROUND: Angiographic parameters can facilitate the risk stratification of coronary lesions but remain insufficient in the prediction of future myocardial infarction (MI). AIMS: We compared the ability of humans, angiographic parameters and deep learning (DL) to predict the lesion that would be responsible for a future MI in a population of patients with non-significant CAD at baseline. METHODS: We retrospectively included patients who underwent invasive coronary angiography (ICA) for MI, in whom a previous angiogram had been performed within 5 years. The ability of human visual assessment, diameter stenosis, area stenosis, quantitative flow ratio (QFR) and DL to predict the future culprit lesion (FCL) was compared. RESULTS: In total, 746 cropped ICA images of FCL and non-culprit lesions (NCL) were analysed. Predictive models for each modality were developed in a training set before validation in a test set. DL exhibited the best predictive performance with an area under the curve of 0.81, compared with diameter stenosis (0.62, p=0.04), area stenosis (0.58, p=0.05) and QFR (0.67, p=0.13). DL exhibited a significant net reclassification improvement (NRI) compared with area stenosis (0.75, p=0.03) and QFR (0.95, p=0.01), and a positive nonsignificant NRI when compared with diameter stenosis. Among all models, DL demonstrated the highest accuracy (0.78) followed by QFR (0.70) and area stenosis (0.68). Predictions based on human visual assessment and diameter stenosis had the lowest accuracy (0.58). CONCLUSION: In this feasibility study, DL outperformed human visual assessment and established angiographic parameters in the prediction of FCLs. Larger studies are now required to confirm this finding.
Mahendiran et al. (Sun,) conducted a observational in Non-significant coronary artery disease. Deep learning (DL) prediction model vs. Human visual assessment, diameter stenosis, area stenosis, and quantitative flow ratio (QFR) was evaluated on Prediction of the future culprit lesion (FCL) (AUC 0.81, p=0.04). Deep learning predicted future culprit lesions with an AUC of 0.81, outperforming diameter stenosis (AUC 0.62, p=0.04), area stenosis (AUC 0.58, p=0.05), and human visual assessment.